collaborators

6 papers

cs.DS2026

Terminal Dimension Reduction for Time Series with Applications

Alexander Munteanu, Matteo Russo, David Saulpic +1

Terminal embeddings have emerged as a powerful tool for dimension reduction. Given a set of points , a terminal embedding is a mapping $f:\mathbb{R}^d\righta…

cs.DS2026

Dimension Reduction for Curves: Simplified and Generalized

Matthijs Ebbens, Jie Lu, Alexander Munteanu

We revisit random projections for reducing the dimension of high-dimensional polygonal curves. Drawing from the toolbox of randomized linear algebra, we give a considerably simplif…

cs.LG2026

Optimal Dimension-Free Sampling for Regularized Classification

Meysam Alishahi, Alexander Munteanu, Simon Omlor +1

We prove optimal sampling bounds achieving -relative error for a broad class of Lipschitz continuous classification loss functions under various regularization t…

cs.LG2026

Scalable Learning of Multivariate Distributions via Coresets

Zeyu Ding, Katja Ickstadt, Nadja Klein +2

Efficient and scalable non-parametric or semi-parametric regression analysis and density estimation are of crucial importance to the fields of statistics and machine learning. Howe…

cs.CG2026

Hardness of High-Dimensional Linear Classification

Alexander Munteanu, Simon Omlor, Jeff M. Phillips

We establish new exponential in dimension lower bounds for the Maximum Halfspace Discrepancy problem, which models linear classification. Both are fundamental problems in computati…

cs.DS2025

Improved Learning via k-DTW: A Novel Dissimilarity Measure for Curves

Amer Krivošija, Alexander Munteanu, André Nusser +1

This paper introduces -Dynamic Time Warping (-DTW), a novel dissimilarity measure for polygonal curves. -DTW has stronger metric properties than Dynamic Time Warping (DTW)…